-
I am trying to explain a customly trained USE model from the TFHub.
The model takes string as inputs.
I get this while trying to call the explainer function:
```
root@d0c5d073d95f:/workspace# pyth…
-
When running shap.KernelExplainer with the option keep_index = True, there is the following error:
```
explainer = shap.KernelExplainer(predict_AE_XAI_SHAP_API, X_real_XAI, keep_index = True)
exp…
-
### Problem Description
See https://github.com/shap/shap/blob/94c64e375f6680c61bca13b5a38ce162a95cf5d9/shap/explainers/pytree.py#L220
We have support now only for xgboost
```python
def shap_…
-
DALEX returns a set of statistics for SHAP (e.g., min, median, mean, max). Only means are used currently.
-
SHAP~HEAD
- This issue ONLY arises for certain random datasets (e.g. if we change the seed sometimes it works!)
- Additionally, if we comment out the model.predict_proba() step, there is also no e…
-
I am trying to use shap with an LSTM and data with 4 time periods so my datasets typically look like (num_rows,4,num_features). Because DeepExplainer is not compatible with Tensorflow 2.x, I have been…
-
We have this conflict between tensorflow and shap, where tensorflow 2.5 cannot work with numpy >=1.20.0 and shap is compiled with numpy API version 0xe (numpy >=1.20.0 I believe, the current installat…
-
_Hi,
having troubles with using the deep explainer with Keras TF2. I'm using a simple model like they below:_
``
`def rnn_model(embedding_dim, max_words, input_length, mod_type):
model =…
-
How Could I explain the model? Is there any way? Like using LIME or SHAP?
-
When I am trying to draw multiple plots in one figure, the layout is messed up:
1. firstly the position of the bar on the right becomes "global" for the figure
2. only the 1st ax is treated correctl…